Papers with Code 아카이브
Unsupervised Video Object Segmentation
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 0
- 평가표
- 6
- 보존된 평가 기록
- 76
The unsupervised scenario assumes that the user does not interact with the algorithm to obtain the segmentation masks. Methods should provide a set of object candidates with no overlapping pixels that span through the whole video sequence. This set of objects should contain at least the objects that capture human attention when watching the whole video sequence i.e objects that are more likely to be followed by human gaze.
코드
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
https://github.com/GewelsJI/FSNet
공식 코드https://github.com/Hydragon516/PMN
공식 코드Unsupervised Video Object Segmentation via Prototype Memory Network
https://github.com/JingchunCheng/SegFlow
공식 코드SegFlow: Joint Learning for Video Object Segmentation and Optical Flow
https://github.com/Liusifei/UVC
공식 코드Joint-task Self-supervised Learning for Temporal Correspondence
https://github.com/MSiam/motion_adaptation
공식 코드https://github.com/NUST-Machine-Intelligence-Laboratory/HFAN
공식 코드Hierarchical Feature Alignment Network for Unsupervised Video Object Segmentation
https://github.com/TonyLianLong/RCF-UnsupVideoSeg
공식 코드Bootstrapping Objectness from Videos by Relaxed Common Fate and Visual Grouping
https://github.com/VisionTao/UOVOS
공식 코드Unsupervised Online Video Object Segmentation with Motion Property Understanding
https://github.com/alibaba/uvosam
공식 코드UVOSAM: A Mask-free Paradigm for Unsupervised Video Object Segmentation via Segment Anything Model
https://github.com/bit-ml/sfseg
공식 코드A 3D Convolutional Approach to Spectral Object Segmentation in Space and Time
https://github.com/carrierlxk/AGNN
공식 코드Zero-Shot Video Object Segmentation via Attentive Graph Neural Networks
https://github.com/carrierlxk/COSNet
공식 코드See More, Know More: Unsupervised Video Object Segmentation with Co-Attention Siamese Networks
https://github.com/carrierlxk/MuG
공식 코드https://github.com/dvlab-research/proposereduce
공식 코드https://github.com/griffbr/TIS
공식 코드https://github.com/griffbr/supervoxel-gerrymandering
공식 코드Video Object Segmentation using Supervoxel-Based Gerrymandering
https://github.com/hkchengrex/Tracking-Anything-with-DEVA
공식 코드https://github.com/hy0523/mtnet
공식 코드Learning Motion and Temporal Cues for Unsupervised Video Object Segmentation
https://github.com/hydragon516/dpa
공식 코드Dual Prototype Attention for Unsupervised Video Object Segmentation
https://github.com/hydragon516/gsanet
공식 코드Guided Slot Attention for Unsupervised Video Object Segmentation
https://github.com/imatge-upc/rvos
공식 코드RVOS: End-to-End Recurrent Network for Video Object Segmentation
https://github.com/mfaisal59/EpONet
공식 코드EpO-Net: Exploiting Geometric Constraints on Dense Trajectories for Motion Saliency
https://github.com/pansanity666/INO_VOS
공식 코드In-N-Out Generative Learning for Dense Unsupervised Video Segmentation
https://github.com/ponimatkin/ssl-vos
공식 코드A Simple and Powerful Global Optimization for Unsupervised Video Object Segmentation
https://github.com/sabarim/3DC-Seg
공식 코드Making a Case for 3D Convolutions for Object Segmentation in Videos
https://github.com/sabarim/STEm-Seg
공식 코드STEm-Seg: Spatio-temporal Embeddings for Instance Segmentation in Videos
https://github.com/schmiddo/d2conv3d
공식 코드D^2Conv3D: Dynamic Dilated Convolutions for Object Segmentation in Videos
https://github.com/suhwan-cho/tmo
공식 코드Treating Motion as Option to Reduce Motion Dependency in Unsupervised Video Object Segmentation
https://github.com/tfzhou/MATNet
공식 코드Motion-Attentive Transition for Zero-Shot Video Object Segmentation
https://github.com/visinf/dense-ulearn-vos
공식 코드https://github.com/xiaoqi-zhao-dlut/multi-source-aps-zvos
공식 코드Multi-Source Fusion and Automatic Predictor Selection for Zero-Shot Video Object Segmentation
https://github.com/xilin1991/CluterNet
공식 코드Online Unsupervised Video Object Segmentation via Contrastive Motion Clustering
https://github.com/xilin1991/IMCNet
공식 코드Implicit Motion-Compensated Network for Unsupervised Video Object Segmentation
https://github.com/yz93/anchor-diff-VOS
공식 코드https://github.com/zlai0/CorrFlow
공식 코드출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.